Browsing by Author "Mueller, Felicitas"

Now showing 1 - 3 of 3

Comparison of machine learning and MPC methods for control of home battery storage systems in distribution grids
(Elsevier, 2025-08-02) Mueller, Felicitas; de Jongh, Steven; Cañizares, Claudio A.; Leibfried, Thomas; Bhattacharya, Kankar
Control methods for Home Energy Management Systems implemented with traditional optimization techniques and state-of-the-art Machine Learning methods are presented and compared in this paper in the context of their impact on and interactions with Active Distribution Networks. Thus, model-based methods based on Model Predictive Control algorithms with different prediction qualities are first described and compared against model-free methods based on imitation learning and reinforcement learning. A practical, state-of-the-art, heuristic, rule-based controller is used as the baseline. An in-depth comparison is performed using metrics consisting of objective function values, grid constraint violations, and computational time. The results of applying these Home Energy Management Systems to a realistic German low voltage benchmark grid with 13 connected households, each containing solar generation, a battery storage system, and electrical loads are discussed. It is demonstrated that model-based and model-free methods can achieve improvements over typical rule-based methods, with varying performance in terms of objective function values and grid constraint violations depending on the forecasts, at the cost of higher computational complexity. Furthermore, model-free methods are shown to have in general low computational burden at higher objective function values with more grid constraint violations, with imitation-learning-based techniques proving to be the best compromise for practical applications.
Data-Driven Topology and Parameter Identification in Distribution Systems With Limited Measurements
(Institute of Electrical and Electronics Engineers (IEEE), 2024-11-05) de Jongh, Steven; Mueller, Felicitas; Osterberg, Fabian; Cañizares, Claudio A.; Leibfried, Thomas; Bhattacharya, Kankar
This manuscript presents novel techniques for identifying the switch states, phase identification, and estimation of equipment parameters in multi-phase low voltage electrical grids, which is a major challenge in long-standing German low voltage grids that lack observability and are heavily impacted by modelling errors. The proposed methods are tailored for systems with a limited number of spatially distributed measuring devices, which measure voltage magnitudes at specific nodes and some line current magnitudes. The overall approach employs a problem decomposition strategy to divide the problem into smaller subproblems, which are addressed independently. The techniques for identifying switch states and system phases are based on heuristics and a binary optimization problem using correlation analysis of the measured time series. The estimation of equipment parameters is achieved through a data-driven regression approach and by an optimization problem, and the identification of cable types is solved using a Mixed-Integer Quadratic Programming solver. To validate the presented methods, a realistic grid is used and the presented techniques are evaluated for their resilience to data quality and time resolution, discussing the limitations of the proposed methods.
Distribution Grid State Estimation With Limited Actual and Pseudo Measurements
(Institute of Electrical and Electronics Engineers (IEEE), 2025-06-25) de Jongh, Steven; Mueller, Felicitas; Cañizares, Claudio A.; Leibfried, Thomas; Bhattacharya, Kankar
Methods for distribution system state estimation in Low Voltage (LV) distribution grids are discussed in this paper, for systems with a high penetration of Distributed Energy Resources (DERs) such as solar generators and heatpumps. The proposed methods are specifically designed for LV grids with sparse measurement availability, such as feeders with measurements only at the distribution transformer, as is typically the case in some European LV grids. For these cases, device locations, temporal data, and weather data are used in the proposed techniques to estimate variables at unmeasured grid nodes. The impact of smart meters is also investigated by simulating the impact of individual smart meter measurements on the estimation results. The proposed methods are based on time series disaggregation of transformer measurements, such as thermoelectrical demand, baseload, and solar generation, enabling improvements over existing Pseudo-Measurement (PM) generation techniques. Furthermore, the paper presents approaches for estimating voltages and currents in the feeder using both actual and PMs, based on classical estimation methods and interval estimation techniques for unmeasured variables. The results for an realistic German LV grid show that the proposed disaggregation step allows to significantly improve the results of the state estimation results over state-of-the-art methods.